© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 120595
    Prev
    Next
    INDEX
    Explanations

    making paste

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     underwriters
    0.59
     constraining
    0.59
     reductions
    0.54
    用い
    0.54
     preservatives
    0.53
    <0x88>
    0.53
    মুনা
    0.53
     tambahan
    0.53
     emulsions
    0.53
     투자
    0.52
    POSITIVE LOGITS
     Form
    0.64
    ädt
    0.58
     Acest
    0.58
     وصل
    0.56
    ς
    0.55
     પાસે
    0.55
     Syk
    0.55
     Sensory
    0.54
    highscore
    0.53
    oc
    0.53
    Activations Density 0.014%

    No Known Activations